Superpixel tracking via graph-based semi-supervised SVM and supervised saliency detection

Abstract

This paper proposes a superpixel tracking method via a graph-based hybrid discriminative-generative appearance model. By utilizing a superpixel-based graph structure as the visual representation, spatial information between superpixels is considered. For constructing the discriminative appearance model, we propose a graph-based semi-supervised support vector machine (SVM) approach by taking superpixels in the current frame as unlabeled training samples and adjusting the classification result utilizing the spatial information provided by a k-regular graph, making the tracker more robust for appearance variation. The adjusted classification result is further used in graph-based supervised saliency detection to generate a generative appearance model, making the real target more salient. Finally, we incorporate the hybrid appearance model into a particle filter framework. Experimental results on five challenging sequences demonstrate that our tracker is robust in dealing with occlusion and shape deformation.